qwen / text-generation API-only released 2026-07-27

Qwen3.7 Flash

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

Input / 1M
$0.03
Output / 1M
$0.13
Context
1M
AA Intelligence
—
Closed weights — available only as a hosted API text + image + video → text View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-10-24
$0.03
input / 1M
$0.13
output / 1M
$0.006
cached input / 1M
$0.16
1M in + 1M out
Price tiers
  • Above 32K prompt tokens: input $0.10/M, output $0.40/M (3.33× base)
  • Above 256K prompt tokens: input $0.20/M, output $0.80/M (6.67× base)
Context window
1,000,000 tokens
Max output
65,536 tokens
Providers
1
Cheapest provider
Alibaba · $0.03 / $0.13
Best throughput
—
AA Intelligence / Coding / Agentic
— / — / —
✓ Tool calling ✓ Reasoning ✓ Structured outputs ✓ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (6 recorded)
Current: $0.03 input · $0.13 output per 1M tokens

Providers

1 provider · per 1M tokens · last 30 min metrics
ProviderQuantContextInputOutputUptimeTok/s
Alibaba unknown 1M $0.03 $0.13 100% —
Alibaba unknown 1M $0.035 $0.15 100% —
Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation
qwen
Released on OpenRouter
2026-07-27
Context window
1,000,000 tokens
Max output
65,536 tokens
Input
text, image, video
Output
text
Tokenizer
Qwen
Moderated by provider
No
OpenRouter id
qwen/qwen3.7-flash
Compare with
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.